© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38111
    Prev
    Next
    INDEX
    Explanations

    superscript numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FAKE
    -0.82
    sisting
    -0.79
    orti
    -0.76
    lounge
    -0.75
    citizens
    -0.73
     existing
    -0.73
    fehlungen
    -0.73
    queous
    -0.72
    ቂ
    -0.72
    highway
    -0.71
    POSITIVE LOGITS
    umina
    0.82
    новые
    0.75
    âmara
    0.75
     cantantes
    0.73
    เรีย
    0.73
     .
    0.73
    🖱
    0.72
     pleasantly
    0.71
    zdě
    0.70
     Ramón
    0.69
    Activations Density 0.002%

    No Known Activations